JuneYaooo

JuneYaooo / nihaixia

Public

倪海厦中医课程资料的 Agent Skill：支持课程检索、方证穴位辨析、学习笔记整理与板书截图证据索引。 | An Agent Skill for Ni Haixia TCM course study, formula-pattern lookup, acupoint reference, and screenshot evidence indexing.

acupuncture agent-skills claude-code-skills codex-skill nihaixia
46
9
80% credibility
Found May 29, 2026 at 50 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

This project organizes Ni Haixia's traditional Chinese medicine courses into a searchable knowledge base that works with AI assistants. Users can ask questions in plain language about symptoms, herbal formulas, acupuncture points, and course materials. The system includes nearly 3000 screenshots from actual lectures and covers 14 major course modules. It explicitly includes safety boundaries reminding users that this is for educational study, not medical diagnosis or prescription.

How It Works

1
📚 You discover Ni Haixia's TCM courses

You've heard about Ni Haixia's famous traditional Chinese medicine teachings and want to study them systematically.

2
🤖 You connect the course library to your AI assistant

You install this skill into your AI assistant so it can understand and search through thousands of hours of course materials.

3
💬 You ask questions in plain language

Instead of knowing all the medical terms, you simply ask things like 'Why do some people feel cold when they have a cold, while others feel hot?'

4
You choose how to explore
📖
Browse course modules

Jump into specific courses like Shanghan Lun, Huangdi Neijing, or acupuncture lessons

🖼️
Find lecture screenshots

Search through 2986+ images from the actual course slides and notes

⚖️
Compare formulas and points

Compare different herbal formulas or acupuncture points side by side

5
📝 You get organized study materials

Your AI assistant pulls together relevant lessons, screenshots, and explanations into a clear study guide.

🎓 You learn with clear boundaries

You study confidently knowing the assistant will remind you to consult real doctors for actual health decisions.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 50 to 46 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is nihaixia?

Nihaixia packages Ni Haixia's extensive Traditional Chinese Medicine course materials into a searchable agent skill. Built in Python, it lets you query everything from Shanghan Lun formulas to acupuncture point protocols using plain language. The system indexes over 2,900 screenshot references from the original course lectures, so you get actual visual evidence alongside text summaries. It works as a skill for Claude Code, Codex, and OpenClaw agents.

Why is it gaining traction?

This fills a real gap for developers studying TCM who want structured access to Ni Haixia's teaching rather than digging through hours of video. The "plain language to clinical terminology" translation layer is the killer feature—you describe symptoms in everyday terms and it maps them to the course's diagnostic framework. The screenshot evidence indexing is genuinely useful for visual learners who want to see the original lecture boards. Installation is dead simple: one shell script handles all three supported agents.

Who should use this?

TCM students and practitioners working through Ni Haixia's human legacy courses will get the most value. Developers building agent skills or exploring knowledge retrieval patterns will find the codebase a practical reference. If you're studying Shanghan Lun, Jin Gui, or acupuncture and want course materials organized by formula, acupoint, or lesson sequence, this saves significant manual searching.

Verdict

Use it if you are actively studying Ni Haixia's courses and want structured, searchable access with visual evidence. The credibility score of 0.80% and modest star count reflect early-stage development, but the documentation is thorough and the core functionality works as described. This is a niche tool with clear purpose—adopt it for its specific use case, not as a general-purpose solution.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.